< cd ../gallery
Unified KV-cache compression for LLM inference: 12 Python-native methods, Debian-tested isolated add-ons, Godzilla KVarN/TriAttention, exact Godzilla/Gigatoken profiles, CUDA weight sharing, and multi-GPU planning. Maintained by aivrar on GitHub, where it has earned 25 stars from the community.
# install
pip install multi-turboquantmore vLLM repos
AI & ML
First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss. Maintained by OnlyTerp on GitHub, where it has earned 78 stars from the community.
4mo ago
AI & ML
Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → parallelism → vLLM/SGLang, with GPU labs on open models. Maintained by jiahongsigma on GitHub, where it has earned 20 stars from the community.
3mo ago
AI & ML
Training-free KV cache compression via E8 lattice VQ. 2-bit KV that preserves retrieval (30/30 NIAH vs TurboQuant 0/30). Calibration-free, 9 architectures validated. Maintained by jagmarques on GitHub, where it has earned 24 stars from the community.
2mo ago
